Impute data using the MAGIC algorithm

This is a helper function that imputes data using a pre-computed Marcov matrix. It minimizing the number of matrix multiplications needed to compute a given set of matrix powering operations. The exponents (t_param) must be integers from 1 to 36.

multi_t_fast_impute(data, L, t_param)

Arguments

data

An expression matrix where cells correspond to rows and genes correspond to columns

t_param

A vector of integers ranging from 1 to 32

marcov_mat

A Markov matrix in dgCMatrix format where cells correspond to rows and to columns

Value

A list that includes the following elements:

imputed_data

A cell by gene matrix of the imputed gene expression values.

diffusion_map

A cell by diffusion map component matrix.

affinity_matrix

A cell by cell matrix of the unpowered markov affinity matrix.

Author

Kevin Brulois